{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.25240", "kind": "paper", "url": "https://arxiv.org/abs/2605.25240"}], "authors": ["Russell Yang", "Ruishi Chen", "Pierce Kelaita", "Riya Ranjan", "Sibo Ma", "Charles Dickens", "Matthew Guillod", "Megan Ma", "Julian Nyarko"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.25240", "source_url": "https://arxiv.org/abs/2605.25240"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "A dataset of 30 legal tasks with rubric scores and pairwise preference judgments from practicing attorneys, used to compare rubric-based scoring and comparative judgment."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.25240", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.25240", "title": "JudgmentBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Stanford University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.25240", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.25240", "source_url": "https://openalex.org/W7162409075"}, "key": "claire-radar:2605.25240", "modality": null, "name": "JudgmentBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_judgmentbench_729b2b9c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "644c3226455c8c771bd55962405ef26c25099846caa1c5b7029aa7d94cce9829", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.25240"}, "publisher": null, "released": "2026-05-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.25240", "source_url": "https://arxiv.org/abs/2605.25240"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-25240", "source": "claire_radar", "source_benchmark_id": "2605.25240", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2605.25240", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "6b8af1641e28f6c294d26b4cb93e1748d5c39742fa028ea514761628a1273283", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A dataset of 30 legal tasks with rubric scores and pairwise preference judgments from practicing attorneys, used to compare rubric-based scoring and comparative judgment.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We release JudgmentBench, a benchmark of 30 real-world legal tasks, paired with 1,539 rubric scores and 1,530 pairwise preference judgments collected from practicing attorneys--including at major U.S."}, "familyId": "bmf_4b9658370bd4", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_judgmentbench_729b2b9c", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.25240", "paper": "https://arxiv.org/abs/2605.25240", "pdf": "https://arxiv.org/pdf/2605.25240", "project": null, "report": "https://arxiv.org/abs/2605.25240"}, "metrics": [], "motivation": "Two methodologies dominate current practices of benchmarking: rubric-based scoring evaluates items against predefined criteria, whereas comparative judgment elicits pairwise preferences between outputs.", "name": "JudgmentBench", "oneLine": "A dataset of 30 legal tasks with rubric scores and pairwise preference judgments from practicing attorneys, used to compare rubric-based scoring and comparative judgment.", "paperTitle": "JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.25240", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-24", "source": {"authors": ["Russell Yang", "Ruishi Chen", "Pierce Kelaita", "Riya Ranjan", "Sibo Ma", "Charles Dickens", "Matthew Guillod", "Megan Ma", "Julian Nyarko"], "categories": ["cs.CL", "cs.AI", "cs.CY"], "id": "2605.25240", "title": "JudgmentBench: Comparing Rubric and Preference Evaluation for Quality Assessment", "type": "arxiv", "url": "https://arxiv.org/abs/2605.25240"}, "sourceUpdatedAt": "2026-06-04T00:43:30Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Supports research on expert judgment elicitation and aggregation in domains without ground truth."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
